Research on potato disease identification based on RegNet network

doi:10.13733/j.jcam.issn.2095-5553.2024.06.034

Abstract

Abstract:

In order to overcome the problems of solidified structure of traditional network model and low recognition rate of potato diseases, five types of potato diseases in PlantVillage dataset are taken as the research object, and the images are randomly zoomed in and out, horizontally flipped, vertically flipped and so on for data enhancement. Then a RegNet network model with a high degree of flexibility is designed using a networkbased design space idea, and the PoLy loss function is used to improve RegNet and the attention mechanism is added to predict the potato disease images after data enhancement, and the traditional network models are compared with AlexNet and GoogLeNet. The experimental results show that the improved RegNetX has good performance in potato recognition, the highest accuracy can reach 99.8%, and the model accuracy is higher than AlexNet and GoogLeNet, which can be used as a reference for potato disease recognition.

Key words: potato, crop diseases, RegNet network, image recognition, network design space

摘要：

为克服传统网络模型结构固化、对马铃薯病害识别率低的问题，以PlantVillage数据集中的五类马铃薯病害为研究对象，对图像进行随机放大缩小、水平翻转、垂直翻转等操作进行数据增强。使用一种基于网络设计空间思想设计出具有高度灵活性的RegNet网络模型，利用PoLy损失函数对RegNet进行改进，并加入注意力机制，对数据增强后的马铃薯病害图片进行预测，再与传统网络模型AlexNet和GoogLeNet进行对比。试验结果表明：改进后的RegNetX在马铃薯识别方面具有良好的性能，最高准确率可达99.8%，模型准确率超过AlexNet与GoogLeNet，可为马铃薯病害识别作参考。

关键词: 马铃薯, 农作物病害, RegNet网络, 图像识别, 网络设计空间

CLC Number:

Shi Fang, Wang Ying, Wang Xinfa, Ma Yukun. Research on potato disease identification based on RegNet network [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(6): 229-234.

石放, 王莹, 王新法, 马玉琨. 基于RegNet网络的马铃薯病害识别研究[J]. 中国农机化学报, 2024, 45(6): 229-234.

References

［1］　徐岩, 李晓振, 吴作宏, 等. 基于残差注意力网络的马铃薯叶部病害识别［J］. 山东科技大学学报(自然科学版), 2021, 40(2): 76-83.

Xu Yan, Li Xiaozhen, Wu Zuohong, et al. Potato leaf disease recognition via residual attention network ［J］. Journal of Shandong University of Science and Technology (Natural Science), 2021, 40(2): 76-83.

［2］　蒲秀夫, 宁芊, 雷印杰, 等. 基于二值化卷积神经网络的农业病虫害识别［J］. 中国农机化学报, 2020, 41(2): 177-182.

Pu Xiufu, Ning Qian, Lei Yinjie, et al. Identification of agricultural plant diseases based on binarized convolutional neural network ［J］. Journal of Chinese Agricultural Mechanization, 2020, 41(2): 177-182.

［3］　赵建敏, 芦建文. 基于字典学习的马铃薯叶片病害图像识别算法［J］. 河南农业科学, 2018, 47(4): 154-160.Zhao Jianmin, Lu Jianwen. Identification algorithm of potato diseases on leaves using dictionary learning theory ［J］. Journal of Henan Agricultural Sciences, 2018, 47(4): 154-160.

［4］　姜敏, 沈一鸣, 张敬尧, 等. 基于深度学习的水稻病虫害诊断方法研究［J］. 洛阳理工学院学报(自然科学版), 2019, 29(4): 78-83.

Jiang Min, Shen Yiming, Zhang Jingyao, et al. Research on rice diseases and pests diagnosis based on deep learning ［J］. Journal of Luoyang Institute of Science and Technology (Natural Science Edition), 2019, 29(4): 78-83.

［5］　党满意, 孟庆魁, 谷芳, 等. 基于机器视觉的马铃薯晚疫病快速识别［J］. 农业工程学报, 2020, 36(2): 193-200.

Dang Manyi, Meng Qingkui, Gu Fang, et al. Rapid recognition of potato late blight based on machine vision ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(2): 193-200.

［6］　于洪涛, 袁明新, 王琪, 等. 基于VGG-F动态学习模型的苹果病虫害识别［J］. 科学技术与工程, 2019, 19(32): 249-253.Yu Hongtao, Yuan Mingxin, Wang Qi, et al. Recognition of apple pests and diseases based on VGG-F dynamic leaming model ［J］. Science Technology and Engineering, 2019, 19(32): 249-253.

［7］　牛冲, 牛昱光, 李寒, 等. 基于图像灰度直方图特征的草莓病虫害识别［J］. 江苏农业科学, 2017, 45(4): 169-172.Niu Chong, Niu Yuguang, Li Han, et al. Strawberry disease recognition based on image gray histogram feature ［J］. Jiangsu Agricultural Science, 2017, 45(4): 169-172.

［8］　王林柏, 张博, 姚竟发, 等. 基于卷积神经网络马铃薯叶片病害识别和病斑检测［J］. 中国农机化学报, 2021, 42(11): 122-129.

Wang Linbai, Zhang Bo, Yao Jingfa, et al. Potato leaf disease recognition and potato leaf disease spot detection based on Convolutional Neural Network ［J］. Journal of Chinese Agricultural Mechanization, 2021, 42(11): 122-129.

［9］　赵晋陵, 詹媛媛, 王娟, 等. 基于SEUNet的冬小麦种植区域提取方法［J］. 农业机械学报, 2022, 53(9): 189-196.

Zhao Jinling, Zhan Yuanyuan, Wang Juan, et al. SEUNetBased extraction of winter wheat planting areas ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(9): 189-196.

［10］　张为, 李璞. 基于注意力机制的人脸表情识别网络［J］. 天津大学学报(自然科学与工程技术版), 2022, 55(7): 706-713.

Zhang Wei, Li Pu. Facial expression recognition network based on attention mechanism ［J］. Journal of Tianjin University (Science and Technology), 2022, 55(7): 706-713.

［11］　黄海松, 陈星燃, 韩正功, 等. 基于多尺度注意力机制和知识蒸馏的茶叶嫩芽分级方法［J］. 农业机械学报, 2022, 53(9): 399-407, 458.

Huang Haisong, Chen Xingran, Han Zhenggong, et al. Tea buds grading method based on multiscale attention mechanism and knowledge distillation ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(9): 399-407, 458.

［12］　殷献博, 邓小玲, 兰玉彬, 等. 基于改进YOLOX-Nano算法的柑橘梢期长势智能识别［J］. 华南农业大学学报, 2023, 44(1): 142-150.

Yin Xianbo, Deng Xiaoling, Lan Yubin, et al. Intelligent recognition of citrus shoot growth based on improved YOLOXNano algorithm ［J］. Journal of South China Agricultural University, 2023, 44(1): 142-150.

［13］　于雪莹, 高继勇, 王首程, 等. 基于生成对抗网络和混合注意力机制残差网络的苹果病害识别［J］. 中国农机化学报, 2022, 43(6): 166-174.

Yu Xueying, Gao Jiyong, Wang Shoucheng, et al. Apple disease recognition based on Wasserstein generative adversarial networks and hybrid attention mechanism residual network ［J］. Journal of Chinese Agricultural Mechanization, 2022, 43(6): 166-174.

［14］　高荣华, 白强, 王荣, 等. 改进注意力机制的多叉树网络多作物早期病害识别方法［J］. 计算机科学, 2022, 49(S1): 363-369.

Gao Ronghua, Bai Qiang, Wang Rong, et al. Multitree network multicrop early disease recognition method based on improved attention mechanism ［J］. Computer Science, 2022, 49(S1): 363-369

［15］　杨玥, 冯涛, 梁虹, 等. 融合交叉注意力机制的图像任意风格迁移［J］. 计算机科学, 2022, 49(S1): 345-352, 396.

Yang Yue, Feng Tao, Liang Hong,et al. Image arbitrary style transfer via crisscross attention ［J］. Computer Science, 2022, 49(S1): 345-352, 396.

［16］　高雨亮, 徐向英, 章永龙, 等. 融合分组注意力机制的水稻病虫害图像识别算法［J］. 扬州大学学报(自然科学版), 2021, 24(6): 53-57.

Gao Yuliang, Xu Xiangying, Zhang Yonglong, et al. Image recognition algorithm of rice diseases and insect pests based on shuffle attention mechanism ［J］. Journal of Yangzhou University (Natural Science Edition), 2021, 24(6): 53-57.

［17］　毛腾跃, 宋阳, 郑禄. 基于多尺度与混合注意力机制的苹果目标检测［J］. 中南民族大学学报(自然科学版), 2022, 41(2): 235-242.

Mao Tengyue, Song Yang, Zheng Lu. Apple target detection based on multiscale and hybrid attention mechanism ［J］.Journal of SouthCentral Minzu University (Natural Science Edition), 2022, 41(2): 235-242.

［18］　骆润玫, 殷惠莉, 刘伟康, 等. 基于YOLOv5-C的广佛手病虫害识别［J］. 华南农业大学学报, 2023, 44(1): 151-160.

Luo Runmei, Yin Huili, Liu Weikang, et al. Identification of bergamot pests and diseases in complex background using YOLOv5-C algorithm ［J］. Journal of South China Agricultural University, 2023, 44(1): 151-160.

［19］　Leng Z, Tan M, Liu C, et al. PolyLoss: A polynomial expansion perspective of classification loss functions ［C］. International Conference on Learning Representations (ICLR), 2022.

［20］　Radosavovic I, Kosaraju R P, Girshick R, et al. Designing network design spaces ［C］. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

[1]	Huang Yiqi, Lu Linfei, Shen Hao, , Wang Fukuan, , Qiao Xi, . Research on invading insect recognition based on convolutional neural network [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(7): 222-227.
[2]	Cui Zhongkai, Zhou Jin, Di Zhifeng, Jiang Wei, Li Na, Zhang Hua. Design and experiment of 4UJ-1700 sweet potato stem chopping machine [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(6): 8-12.
[3]	Xu Yalei, Yang Hongguang, Pan Zhiguo, Yang Ranbing, , Li Lin, Zhang Huan. Development of oblique-planting mechanism for sweet potato seedlings and its electric control system [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(6): 53-57.
[4]	Hou Haimin, Shen Mengjiao, Zhang Yan. Analysis of key technologies for crop disease detection [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(6): 90-97.
[5]	Li Longjie, Shi Yong, , Liu Yancen, , Guo Junxian, . Research on predicting Hami melon leaf chlorophyll based on RGB image processing [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(6): 149-155.
[6]	Huang Yao, He Jing, Fu Rao, Liu Gang, , Lin Yuanyang. Application analysis of the YOLOv5s-CBAM algorithm for the identification of eggs of Pomacea [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(6): 223-228.
[7]	Guo Hongjie, Ma Rui, Wang Jia, Zhao Wei, Ma Dexin. Research on apple leaf disease image recognition based on convolutional neural network [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(5): 239-245.
[8]	Zhou Baidong, Niu Qi, Yu Wei, Xie Shouyong, , Wang Lihong, , Li Chengsong, . Discrete element simulation research and optimization of doublechannel vibration potato seed feeder [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(4): 23-31.
[9]	Wang Ling, Zhang Jinxiong, Tian Hui, Zhang Zhujun, Zhao Shuhan. Automatic reading of wheat microprecipitation values based on image processing [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(4): 149-154.
[10]	Ma Zhiyan, , Li Hui, Yang Guangyou, . Research on key technologies of intelligent tea picking machine based on YOLOv3 algorithm [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(4): 199-204.
[11]	Deng Yun, , Feng Qiyao, , Niu Zhaowen, , Kang Yanping, . Finegrained classification of crop diseases and pests based on progressive growing of GANs [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(3): 156-162.
[12]	Sun Weixiao, Liu Faying, Yang Zhenyu, , Han Mengjie, Li Xueqiang, Wei Zhongcai. Classification of potato and impurities based on active thermal infrared imaging [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(2): 143-150.
[13]	Han Mengjie, Liu Faying, Yang Zhenyu, , Sun Weixiao, Chen Xiao, Wei Zhongcai, Li Xueqiang. tudy on recognition method of seed potato bud eye based on laser 3D reconstruction [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(2): 200-206.
[14]	Niu Yuxia, , Sun Zhouhong, Ren Wei, , Chen Linlin, , Chen Lili, . Few-shot potato disease leaf detection based on hierarchical feature alignment network [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(2): 250-258.
[15]	Bai Yupeng, Feng Yikun, Li Guohou, Zhao Mingfu, Zhou Haoyu, Hou Zhisong, . Algorithm of wheat disease image identification based on Vision Transformer [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(2): 267-274.